Computer Vision Engineer

Key Skills

Algorithms, C++, Ceres, Computer Vision (CV), Deep Learning, Docker, Kubernetes-K8s, Linux Operating system, Machine learning techniques, OpenCV, Python Programming, PyTorch, ROS1, TensorFlow, Unix Operating system

Job Description

Fyusion is a leading machine learning and computer vision company focused on automotive inspections and related applications. Our patented 3D format enables anyone to capture and display interactive 3D images using their smartphone, and enables significant added functionality with deep visual understanding and machine learning-driven analysis.

Founded in 2014, Fyusion is now part of the Cox Automotive family. Our team includes some of the world's top researchers and developers in light field imaging and AI, continuing to push boundaries and innovate at the highest level from our San Francisco research center.

The Computer Vision team at Fyusion develops and applies state of the art algorithms in visualization, 3D reconstruction, SLAM, bundle adjustment, state estimation, and sensor fusion. We combine this with the efforts from our Damage Analysis team to deliver an intelligent product which is loved by our customers.

This role will work with our best-in-class Research, Engineering and Product teams for improving and enriching our current solutions, helping scale them to hundreds of physical locations, handling thousands of vehicles per week, and bringing new ideas to reality. This is a high-impact role that will give the opportunity to shape products used millions of times per month and that are revolutionizing the car buying experience. You will be working collaboratively with other members of the research team solving complex problems at the intersection of classical 3D geometry and Deep Learning.

Here’s the day-to-day:

• Work in a fast paced environment developing software in C++ and Python
• Participate in the engineering life-cycle at Fyusion, including designing systems, writing production code, conducting code reviews and working alongside our Design, Engineering, and QA teams
• Brainstorm new ideas and products with a very international, multi-cultural team

Here's what we're looking for:

• MS degree in Computer Science, Engineering or a related subject
• 2+ years of experience with developing efficient computer vision algorithms/models
• Proficient in C++ and Python
• Experience in 3D Deep Learning
• Experience of working with cameras or image data for computer vision applications
• Experience in a Deep Learning framework such as Tensorflow or Pytorch
• Experience with containerization ecosystems such as Docker and Kubernetes
• Good knowledge on C++ build systems and more specifically CMake
• Solid understanding on Unix/Linux environments

Bonus if you have:

• Experience with SLAM, Structure from Motion, bundle adjustment, view synthesis
• Experience with open-source libraries such as OpenCV/ROS/GTSAM/ceres
• Good knowledge on versioning control and packaging software
• Experience with using state-of-the-art open-source libraries from CV research community
• Experience with CI and CD pipelines (Github Actions/Jenkins/Travis)